Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SAMPLE
    -0.08
    有价值
    -0.07
    _s
    -0.07
    好き
    -0.07
     Character
    -0.07
     смысл
    -0.07
    ISBN
    -0.07
    YLeaf
    -0.06
     né
    -0.06
    .on
    -0.06
    POSITIVE LOGITS
    亭
    0.07
     Hawaii
    0.07
    -transparent
    0.07
     atau
    0.07
     trips
    0.07
    ↓
    0.07
     pointed
    0.06
    —or
    0.06
    Exchange
    0.06
    相关部门
    0.06
    Act Density 0.002%

    No Known Activations